RUC's AutoMaster: Skill-guided post-training makes the same model a better teacher
RUC-AIBOX · hf · 2026-11-20
RUC's AutoMaster is an autonomous post-training system built on Skill-FT: natural-language skills steer teacher rollouts to suppress bad habits and elicit underrepresented effective behaviors, then the resulting trajectories fine-tune the target model. An LLM agent handles trajectory analysis, skill design, data selection and feedback. Across Terminal, Search and SWE tasks with 4B/9B models it beats Vanilla SFT on unguided teacher trajectories by 1.42–8.99 points; keeping skill instructions during SFT consistently helps, suggesting better behavioral internalization.
More from Research
- ICLR 2027 desk-rejects papers after reviewers fail to file AI-use disclosure forms — algo_diver · 2026-11-20
- Chorus paper: shared n-gram tables cut memory 87% while beating DeepSeek's Engram — brown2green · 2026-11-20
- Synthetic benchmarks for concept bottleneck models isolate failure modes, NeurIPS 2026 — berkustun · 2026-11-20
- Inhabitant: training-free LLM agent completes 74/75 long-horizon household tasks — Yao Zhang · 2026-11-20
- EPFL team unveils unified 3D generative model for structure-based drug design and docking — HannesStaerk · 2026-11-20
- ICLR 2027 Review Score Distribution: 40,160 Submissions, a 3.0 Average Only Ranks Top 14% — May_F1_ · 2026-11-20